|
PureBytes Links
Trading Reference Links
|
<FONT face="Courier New" color=#0000ff
size=2>Let me wade back into the mire by proposing an old idea for
PositionScore: Past performance using the same system being tested. You may say
that past performance is a poor predictor of future gains, but if that's really
fundamentally so, how does the entire backtest itself prove
anything?
<FONT face="Courier New" color=#0000ff
size=2>
<FONT face="Courier New" color=#0000ff
size=2>Simple equity percentage growth is probably not be the best measure of
performance; we've all seen in our backtests how raw CAR gives an incomplete
picture of system performance. So perhaps using CAR/MDD, or Sharpe Ratio, or
Profit Factor, or some other derived performance stat would be
best.
<FONT face="Courier New" color=#0000ff
size=2>
<FONT face="Courier New" color=#0000ff
size=2>OTOH, while past performance may give some sense of the overall
profitability of using a strategy on a particular stock, it seems to predict
something only in a longer term sense. It doesn't tell you much about the
likelihood of success of the one particular signal that's occurring right then.
IOW, it's an inherently slow signal, which may be inappropriate for use as a
PositionScore.
<FONT face="Courier New" color=#0000ff
size=2>
<FONT face="Courier New" color=#0000ff
size=2>Dave
Yahoo! Groups Sponsor
ADVERTISEMENT
Send BUG REPORTS to bugs@xxxxxxxxxxxxx
Send SUGGESTIONS to suggest@xxxxxxxxxxxxx
-----------------------------------------
Post AmiQuote-related messages ONLY to: amiquote@xxxxxxxxxxxxxxx
(Web page: http://groups.yahoo.com/group/amiquote/messages/)
--------------------------------------------
Check group FAQ at: http://groups.yahoo.com/group/amibroker/files/groupfaq.html
Your use of Yahoo! Groups is subject to the Yahoo! Terms of Service.
|